Back to CalculatorDeploy Now
Gemma 4 E2B
HotGoogle's most compact Gemma 4 model with effective 2B parameters, multimodal (text/image/audio), built for on-device deployment
Specifications
SourceArchitectureVISION
Parameters2B
Familygemma
VRAM (Q4)1.0G
Uses Per-Layer Embeddings (PLE) for parameter efficiency. 128K context. Apache 2.0
googlegemmaedgemultimodalaudioreasoningtrending
Build your Local Rig
Ready to run locally? Shop top-tier GPUs on Amazon for the best performance.
Instant Cloud GPUs
Running out of VRAM? Rent a high-end H100 or RTX 4090 on RunPod and deploy in seconds.
Share this Model
Send these specs directly to your community.